Research map / Reinforcement learning / Visual and representation RL
Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
Jiayao Mai, Bangyan Liao, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera, Tailin Wu, Yi Zhou, Peidong Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add NPC learned policy to GNC | Classic GNC · GNC point cloud registration (bunny) | corrector iterations: 783 -> 169 | Improved |
| Add NPC learned policy to GNC | Classic GNC · GNC point cloud registration (cube) | runtime (ms): 89.34 -> 7.86 | Improved |
| Add NPC to GNC | Classic GNC · GNC point cloud registration | accuracy: -1.12 -> -1.11 | No clear effect |
| Add NPC to GNC | Classic GNC · GNC multi-view triangulation (reichstag) | corrector iterations: 142 -> 21 | Improved |
| Add NPC to GNC | Classic GNC · GNC multi-view triangulation (sacre_coeur) | log10 point error: -5.15 -> -4.84 | Hurt |
| Add NPC to Gaussian homotopy | Classic GH · GH 2d Ackley | corrector iterations: 501 -> 359 | Improved |
| Add NPC to Gaussian homotopy | Classic GH · GH Himmelblau | f(x*): 0.00 -> 0.00 | No clear effect |
| Add NPC to homotopy continuation | Classic HC · HC katsura10 | corrector iterations: 39 -> 7 | Improved |
| Add NPC to homotopy continuation | Classic HC · HC UPnP | corrector iterations: 53 -> 29 | Improved |
| Add NPC to annealed Langevin dynamics | Classic ALD · ALD 40-mode GMM | corrector iterations: 410 -> 110 | Improved |
| Add NPC to annealed Langevin dynamics | Classic ALD · ALD 40-mode GMM | Wasserstein-2: 11.57 -> 11.91 | No clear effect |
| Add NPC to Gaussian homotopy on 10d Ackley | Classic GH · GH 10d Ackley | f(x*): 0.01 -> 0.47 | Hurt |
Closest papers by meaning
- Predictor-Corrector Policy Optimization (ICML 2019 · similarity 0.89)
- Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming (TPAMI 2025 · similarity 0.87)
- Improving Model-Based Reinforcement Learning by Converging to Flatter Minima (NeurIPS 2025 · similarity 0.87)
- Efficient Reinforcement Learning by Discovering Neural Pathways (NeurIPS 2024 · similarity 0.86)
- DeepOR: A Deep Reasoning Foundation Model for Optimization Modeling (AAAI 2026 · similarity 0.86)
- Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning (NeurIPS 2021 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
